© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 57796
    Prev
    Next
    INDEX
    Explanations

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     however
    -0.79
    however
    -0.66
    çĦ¶èĢĮ
    -0.59
    However
    -0.55
    åį´æ²¡æľī
    -0.55
     However
    -0.54
    åį´
    -0.53
     porém
    -0.50
    åį»
    -0.50
     jedoch
    -0.49
    POSITIVE LOGITS
    åĩĨå¤ĩ好
    0.26
    æĹģ
    0.24
    lg
    0.24
    çķĮ
    0.23
    opes
    0.23
    anzi
    0.23
    But
    0.23
    ftar
    0.23
    "But
    0.23
     Continental
    0.23
    Activations Density 0.003%

    No Known Activations